{"total":472,"rows":[{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744,"area":null},{"id":"2103.14675","title":"Synthesis of Compositional Animations from Textual Descriptions","created":"2021-03-26","cited_by_count":178,"area":null},{"id":"2210.08964","title":"PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecasting","created":"2022-09-20","cited_by_count":172,"area":null},{"id":"2110.08568","title":"ASFormer: Transformer for Action Segmentation","created":"2021-10-16","cited_by_count":168,"area":null},{"id":"2106.10271","title":"End-to-end Temporal Action Detection with Transformer","created":"2021-06-18","cited_by_count":151,"area":null},{"id":"2307.03759","title":"A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection","created":"2023-07-07","cited_by_count":145,"area":null},{"id":"2104.10054","title":"T2VLAD: Global-Local Sequence Alignment for Text-Video Retrieval","created":"2021-04-20","cited_by_count":103,"area":null},{"id":"2103.09712","title":"Trans-SVNet: Accurate Phase Recognition from Surgical Videos via Hybrid Embedding Aggregation Transformer","created":"2021-03-17","cited_by_count":94,"area":null},{"id":"2210.10352","title":"Temporal Action Segmentation: An Analysis of Modern Techniques","created":"2022-10-19","cited_by_count":85,"area":null},{"id":"2204.02968","title":"Temporal Alignment Networks for Long-term Video","created":"2022-04-06","cited_by_count":84,"area":null},{"id":"2303.12799","title":"Time Series as Images: Vision Transformer for Irregularly Sampled Time Series","created":"2023-03-01","cited_by_count":79,"area":null},{"id":"2303.17959","title":"Diffusion Action Segmentation","created":"2023-03-31","cited_by_count":74,"area":null},{"id":"2110.06915","title":"Object-Region Video Transformers","created":"2021-10-13","cited_by_count":73,"area":null},{"id":"2111.14338","title":"Improving Deep Learning Interpretability by Saliency Guided Training","created":"2021-11-29","cited_by_count":68,"area":null},{"id":"2103.16327","title":"Temporal Memory Relation Network for Workflow Recognition from Surgical Video","created":"2021-03-30","cited_by_count":66,"area":null},{"id":"2103.11264","title":"Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation","created":"2021-03-20","cited_by_count":58,"area":null},{"id":"2205.14022","title":"Future Transformer for Long-term Action Anticipation","created":"2022-05-27","cited_by_count":58,"area":null},{"id":"2209.00638","title":"Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translation","created":"2022-09-01","cited_by_count":55,"area":null},{"id":"2203.14104","title":"Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos","created":"2022-03-26","cited_by_count":50,"area":null},{"id":"2106.01035","title":"Towards Unified Surgical Skill Assessment","created":"2021-06-02","cited_by_count":49,"area":null},{"id":"2101.08540","title":"Activity Graph Transformer for Temporal Action Localization","created":"2021-01-21","cited_by_count":48,"area":null},{"id":"2103.06669","title":"Temporal Action Segmentation from Timestamp Supervision","created":"2021-03-11","cited_by_count":48,"area":null},{"id":"2409.20371","title":"Frequency Adaptive Normalization For Non-stationary Time Series Forecasting","created":"2024-09-30","cited_by_count":47,"area":null},{"id":"2109.03465","title":"A Survey of Sound Source Localization with Deep Learning Methods","created":"2021-09-08","cited_by_count":46,"area":null},{"id":"2205.13947","title":"Spatio-Temporal Graph Few-Shot Learning with Cross-City Knowledge Transfer","created":"2022-05-27","cited_by_count":43,"area":null},{"id":"2101.00910","title":"Global2Local: Efficient Structure Search for Video Action Segmentation","created":"2021-01-04","cited_by_count":42,"area":null},{"id":"2112.03902","title":"MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection","created":"2021-12-07","cited_by_count":42,"area":null},{"id":"2204.13841","title":"An Extensive Data Processing Pipeline for MIMIC-IV","created":"2022-04-29","cited_by_count":40,"area":null},{"id":"2111.12374","title":"MM-Pyramid: Multimodal Pyramid Attentional Network for Audio-Visual Event Localization and Video Parsing","created":"2021-11-24","cited_by_count":39,"area":null},{"id":"2309.13952","title":"VidChapters-7M: Video Chapters at Scale","created":"2023-09-25","cited_by_count":39,"area":null},{"id":"2404.01518","title":"Temporally Consistent Unbalanced Optimal Transport for Unsupervised Action Segmentation","created":"2024-04-01","cited_by_count":38,"area":null},{"id":"2107.13411","title":"Predicting the Future from First Person (Egocentric) Vision: A Survey","created":"2021-07-28","cited_by_count":36,"area":null},{"id":"2112.03612","title":"DCAN: Improving Temporal Action Detection via Dual Context Aggregation","created":"2021-12-07","cited_by_count":36,"area":null},{"id":"2308.11358","title":"How Much Temporal Long-Term Context is Needed for Action Segmentation?","created":"2023-08-22","cited_by_count":36,"area":null},{"id":"2406.12199","title":"Time Series Modeling for Heart Rate Prediction: From ARIMA to Transformers","created":"2024-06-18","cited_by_count":35,"area":null},{"id":"2305.06061","title":"Visual Tuning","created":"2023-05-10","cited_by_count":34,"area":null},{"id":"2302.06492","title":"Optical flow estimation from event-based cameras and spiking neural networks","created":"2023-02-13","cited_by_count":33,"area":null},{"id":"2110.00111","title":"Deep Learning-based Action Detection in Untrimmed Videos: A Survey","created":"2021-09-30","cited_by_count":32,"area":null},{"id":"2111.11631","title":"Self-Regulated Learning for Egocentric Video Activity Anticipation","created":"2021-11-23","cited_by_count":32,"area":null},{"id":"2104.02710","title":"The Multi-Agent Behavior Dataset: Mouse Dyadic Social Interactions","created":"2021-04-06","cited_by_count":31,"area":null},{"id":"2207.09270","title":"Action Quality Assessment with Temporal Parsing Transformer","created":"2022-07-19","cited_by_count":31,"area":null},{"id":"2208.05908","title":"Uncertainty Quantification of Sparse Travel Demand Prediction with Spatial-Temporal Graph Neural Networks","created":"2022-08-11","cited_by_count":29,"area":null},{"id":"2103.01302","title":"Coarse-Fine Networks for Temporal Activity Detection in Videos","created":"2021-03-01","cited_by_count":28,"area":null},{"id":"2105.10859","title":"Coarse to Fine Multi-Resolution Temporal Convolutional Network","created":"2021-05-23","cited_by_count":28,"area":null},{"id":"2206.01038","title":"A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications","created":"2022-06-02","cited_by_count":28,"area":null},{"id":"2303.08011","title":"Model scale versus domain knowledge in statistical forecasting of chaotic systems","created":"2023-03-13","cited_by_count":27,"area":null},{"id":"2105.00067","title":"Unsupervised Discriminative Embedding for Sub-Action Learning in Complex Activities","created":"2021-04-30","cited_by_count":26,"area":null},{"id":"2108.06524","title":"Foreground-Action Consistency Network for Weakly Supervised Temporal Action Localization","created":"2021-08-14","cited_by_count":26,"area":null},{"id":"2102.00027","title":"Gesture Recognition in Robotic Surgery: a Review","created":"2021-01-29","cited_by_count":23,"area":null},{"id":"2104.09907","title":"Table Tennis Stroke Recognition Using Two-Dimensional Human Pose Estimation","created":"2021-04-20","cited_by_count":23,"area":null},{"id":"2107.09504","title":"Multi-Modal Temporal Convolutional Network for Anticipating Actions in Egocentric Videos","created":"2021-07-18","cited_by_count":23,"area":null},{"id":"2111.11044","title":"Exploring Segment-level Semantics for Online Phase Recognition from Surgical Videos","created":"2021-11-22","cited_by_count":23,"area":null},{"id":"2208.11602","title":"Motion Robust High-Speed Light-Weighted Object Detection With Event Camera","created":"2022-08-24","cited_by_count":23,"area":null},{"id":"2212.11078","title":"C2F-TCN: A Framework for Semi and Fully Supervised Temporal Action Segmentation","created":"2022-12-20","cited_by_count":23,"area":null},{"id":"2104.07461","title":"Action Segmentation with Mixed Temporal Domain Adaptation","created":"2021-04-15","cited_by_count":21,"area":null},{"id":"2109.11593","title":"Long Short View Feature Decomposition via Contrastive Video Representation Learning","created":"2021-09-23","cited_by_count":21,"area":null},{"id":"2303.03757","title":"Deep Learning for Inertial Positioning: A Survey","created":"2023-03-07","cited_by_count":21,"area":null},{"id":"2107.04810","title":"Not End-to-End: Explore Multi-Stage Architecture for Online Surgical Phase Recognition","created":"2021-07-10","cited_by_count":20,"area":null},{"id":"2202.01727","title":"Skeleton-Based Action Segmentation with Multi-Stage Spatial-Temporal Graph Convolutional Neural Networks","created":"2022-02-03","cited_by_count":20,"area":null},{"id":"2112.01402","title":"Iterative Contrast-Classify For Semi-supervised Temporal Action Segmentation","created":"2021-12-02","cited_by_count":19,"area":null},{"id":"2203.07976","title":"On the Pitfalls of Batch Normalization for End-to-End Video Learning: A Study on Surgical Workflow Analysis","created":"2022-03-15","cited_by_count":19,"area":null},{"id":"2205.07493","title":"Multi-scale Attention Flow for Probabilistic Time Series Forecasting","created":"2022-05-16","cited_by_count":19,"area":null},{"id":"2206.11517","title":"Utilizing Expert Features for Contrastive Learning of Time-Series Representations","created":"2022-06-23","cited_by_count":17,"area":null},{"id":"2207.08653","title":"Leveraging Action Affinity and Continuity for Semi-supervised Temporal Action Segmentation","created":"2022-07-18","cited_by_count":17,"area":null},{"id":"2207.09425","title":"Geometric Features Informed Multi-person Human-object Interaction Recognition in Videos","created":"2022-07-19","cited_by_count":17,"area":null},{"id":"2302.00431","title":"Do I Have Your Attention: A Large Scale Engagement Prediction Dataset and Baselines","created":"2023-02-01","cited_by_count":17,"area":null},{"id":"2305.19478","title":"Permutation-Aware Action Segmentation via Unsupervised Frame-to-Segment Alignment","created":"2023-05-31","cited_by_count":17,"area":null},{"id":"2306.11052","title":"A spatio-temporal network for video semantic segmentation in surgical videos","created":"2023-06-19","cited_by_count":17,"area":null},{"id":"2312.02638","title":"Synchronization is All You Need: Exocentric-to-Egocentric Transfer for Temporal Action Segmentation with Unlabeled Synchronized Video Pairs","created":"2023-12-05","cited_by_count":17,"area":null},{"id":"2403.09805","title":"On the Utility of 3D Hand Poses for Action Recognition","created":"2024-03-14","cited_by_count":17,"area":null},{"id":"2103.02758","title":"Learning Asynchronous and Sparse Human-Object Interaction in Videos","created":"2021-03-03","cited_by_count":16,"area":null},{"id":"2106.12901","title":"Recurrent Neural Network from Adder's Perspective: Carry-lookahead RNN","created":"2021-06-22","cited_by_count":16,"area":null},{"id":"2108.03894","title":"FIFA: Fast Inference Approximation for Action Segmentation","created":"2021-08-09","cited_by_count":16,"area":null},{"id":"2108.06706","title":"Temporal Action Segmentation with High-level Complex Activity Labels","created":"2021-08-15","cited_by_count":16,"area":null},{"id":"2112.06447","title":"SVIP: Sequence VerIfication for Procedures in Videos","created":"2021-12-13","cited_by_count":16,"area":null},{"id":"2208.00934","title":"Video Question Answering with Iterative Video-Text Co-Tokenization","created":"2022-08-01","cited_by_count":16,"area":null},{"id":"2105.14158","title":"SSCAP: Self-supervised Co-occurrence Action Parsing for Unsupervised Temporal Action Segmentation","created":"2021-05-29","cited_by_count":15,"area":null},{"id":"2110.07922","title":"Anomaly Detection in Multi-Agent Trajectories for Automated Driving","created":"2021-10-15","cited_by_count":15,"area":null},{"id":"2110.13473","title":"CTRN: Class-Temporal Relational Network for Action Detection","created":"2021-10-26","cited_by_count":15,"area":null},{"id":"2302.13752","title":"A Brief Survey on the Approximation Theory for Sequence Modelling","created":"2023-02-27","cited_by_count":15,"area":null},{"id":"2304.05729","title":"Dynamic Graph Representation Learning with Neural Networks: A Survey","created":"2023-04-12","cited_by_count":15,"area":null},{"id":"2308.14500","title":"LAC: Latent Action Composition for Skeleton-based Action Segmentation","created":"2023-08-28","cited_by_count":15,"area":null},{"id":"2101.06636","title":"Coarse Temporal Attention Network (CTA-Net) for Driver's Activity Recognition","created":"2021-01-17","cited_by_count":14,"area":null},{"id":"2112.10194","title":"UnweaveNet: Unweaving Activity Stories","created":"2021-12-19","cited_by_count":14,"area":null},{"id":"2205.08689","title":"Spatial-Temporal Interactive Dynamic Graph Convolution Network for Traffic Forecasting","created":"2022-05-18","cited_by_count":14,"area":null},{"id":"2205.09445","title":"Cross-Enhancement Transformer for Action Segmentation","created":"2022-05-19","cited_by_count":14,"area":null},{"id":"2211.08675","title":"XRBench: An Extended Reality (XR) Machine Learning Benchmark Suite for the Metaverse","created":"2022-11-16","cited_by_count":14,"area":null},{"id":"2310.00608","title":"Skip-Plan: Procedure Planning in Instructional Videos via Condensed Action Space Learning","created":"2023-10-01","cited_by_count":14,"area":null},{"id":"2312.06829","title":"Encoding Surgical Videos as Latent Spatiotemporal Graphs for Object and Anatomy-Driven Reasoning","created":"2023-12-11","cited_by_count":14,"area":null},{"id":"2504.05336","title":"Quantum Adaptive Self-Attention for Quantum Transformer Models","created":"2025-04-05","cited_by_count":14,"area":null},{"id":"2201.02143","title":"Classification of Long Sequential Data using Circular Dilated Convolutional Neural Networks","created":"2022-01-06","cited_by_count":13,"area":null},{"id":"2205.02805","title":"An Empirical Study on Activity Recognition in Long Surgical Videos","created":"2022-05-05","cited_by_count":13,"area":null},{"id":"2204.09434","title":"FenceNet: Fine-grained Footwork Recognition in Fencing","created":"2022-04-20","cited_by_count":12,"area":null},{"id":"2306.04216","title":"MMSum: A Dataset for Multimodal Summarization and Thumbnail Generation of Videos","created":"2023-06-07","cited_by_count":12,"area":null},{"id":"2312.07378","title":"X4D-SceneFormer: Enhanced Scene Understanding on 4D Point Cloud Videos through Cross-modal Knowledge Transfer","created":"2023-12-12","cited_by_count":12,"area":null},{"id":"2503.22405","title":"Modeling Multiple Normal Action Representations for Error Detection in Procedural Tasks","created":"2025-03-28","cited_by_count":12,"area":null},{"id":"2110.05697","title":"Hierarchical Modeling for Task Recognition and Action Segmentation in Weakly-Labeled Instructional Videos","created":"2021-10-12","cited_by_count":11,"area":null},{"id":"2110.06324","title":"A Multi-scale Time-series Dataset with Benchmark for Machine Learning in Decarbonized Energy Grids","created":"2021-10-12","cited_by_count":11,"area":null},{"id":"2204.06947","title":"EEG-ITNet: An Explainable Inception Temporal Convolutional Network for Motor Imagery Classification","created":"2022-04-14","cited_by_count":11,"area":null},{"id":"2309.17257","title":"A Survey on Deep Learning Techniques for Action Anticipation","created":"2023-09-29","cited_by_count":11,"area":null}],"next_cursor":"100"}